© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30859
    Prev
    Next
    INDEX
    Explanations

    serial numbers or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lembrando
    0.49
    plikasi
    0.48
    calcular
    0.47
    உலகின்
    0.47
     Pawar
    0.46
    කාශ
    0.46
    喱
    0.46
    Metaxy
    0.46
    உலக
    0.46
     seductive
    0.45
    POSITIVE LOGITS
     and
    0.52
     t
    0.50
     helps
    0.49
     fairs
    0.49
     be
    0.48
     may
    0.48
     or
    0.46
     makes
    0.46
     tri
    0.45
     who
    0.45
    Activations Density 0.032%

    No Known Activations